EmbeddingAlign RAG: Boosting QA Systems
•
12
Pierre-Louis B PRO
PLB
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 8 hours ago
juniorlabs/unity_dataset
published
a dataset
about 8 hours ago
juniorlabs/unity_dataset
updated
a dataset
1 day ago
PLB/tags-test
Articles
Organizations
PLB's activity
updated
a
dataset
about 8 hours ago
published
a
dataset
about 8 hours ago
updated
a
dataset
1 day ago
published
a
dataset
2 days ago
updated
a
model
9 days ago
published
a
model
9 days ago
updated
a
dataset
12 days ago
published
a
dataset
12 days ago
updated
a
dataset
12 days ago
published
a
dataset
12 days ago
reacted to
thomwolf's
post with 🤯
2 months ago
Post
1448
Very exciting new
mistralai/Pixtral-Large-Instruct-2411 model from Mistral-AI
Impressive performances, huge congrats @patrickvonplaten @sgvaze @pandora-s @devendrachaplot @sophiamyang and team!
Very nice to have SOTA Multilingual OCR and Chart understanding in an open-weights model
Impressive performances, huge congrats @patrickvonplaten @sgvaze @pandora-s @devendrachaplot @sophiamyang and team!
Very nice to have SOTA Multilingual OCR and Chart understanding in an open-weights model
replied to
their
post
2 months ago
We didn't deploy a live version yet. Will ping you when we do so!
posted
an
update
3 months ago
Post
1873
⚠️ People selling AI chatbots for websites hate us.
Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble
How does it work ?
- You give an URL
- The AI assistant crawls the website content and embed it
- Add it to your frontend in one line of code
- People on your website can ask the assistant questions
Powered by BAAI/bge-small-en-v1.5 and Mistral AI
Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble
How does it work ?
- You give an URL
- The AI assistant crawls the website content and embed it
- Add it to your frontend in one line of code
- People on your website can ask the assistant questions
Powered by BAAI/bge-small-en-v1.5 and Mistral AI
-
- 5 replies
upvoted
an
article
3 months ago
Article
Recipe: Preparing Multilingual Speech Datasets for TTS Training
By
•
•
16
replied to
their
post
3 months ago
As always, there is a trade-off to find between generality and absolute performance. If you have multiple different domaines/dataset with a clear separation, I think it would make sens to train an adapter for each domain.
posted
an
update
3 months ago
Post
384
📈 Increase the quality of your RAG with a simple Linear Layer! No need to change your embedding model (keep that old OpenAI API).
Introducing EmbeddingAlign RAG, a novel approach to improve Retrieval-Augmented Generation (RAG) systems.
Key highlights:
- Uses a simple linear transformation on existing embeddings
- Boosts hit rate from 89% to 95% on real-world examples
- Minor increase on latency (less than 10ms)
- Works on top of blackbox embedding models (Mistral AI, OpenAI, Cohere,...)
- No dataset needed (just your documents)
- Train easily on CPU
🤗 Read the full article here on HF: https://huggingface.co/blog/PLB/embedding-align-rag
Introducing EmbeddingAlign RAG, a novel approach to improve Retrieval-Augmented Generation (RAG) systems.
Key highlights:
- Uses a simple linear transformation on existing embeddings
- Boosts hit rate from 89% to 95% on real-world examples
- Minor increase on latency (less than 10ms)
- Works on top of blackbox embedding models (Mistral AI, OpenAI, Cohere,...)
- No dataset needed (just your documents)
- Train easily on CPU
🤗 Read the full article here on HF: https://huggingface.co/blog/PLB/embedding-align-rag
-
- 2 replies
published
an
article
3 months ago
Article
EmbeddingAlign RAG: Boosting QA Systems
By
•
•
12
liked
a
Space
4 months ago
upvoted
an
article
5 months ago
Article
Fine-tuning Parler TTS on a Specific Language
By
•
•
28
liked
a
dataset
5 months ago